CN110517765A - A kind of prostate cancer big data aid decision-making method and system constituting method based on fuzzy reasoning logic - Google Patents
A kind of prostate cancer big data aid decision-making method and system constituting method based on fuzzy reasoning logic Download PDFInfo
- Publication number
- CN110517765A CN110517765A CN201910635587.6A CN201910635587A CN110517765A CN 110517765 A CN110517765 A CN 110517765A CN 201910635587 A CN201910635587 A CN 201910635587A CN 110517765 A CN110517765 A CN 110517765A
- Authority
- CN
- China
- Prior art keywords
- prostate cancer
- patient
- value
- stages
- pev
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
Landscapes
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Public Health (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Epidemiology (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The invention discloses a kind of prostate cancer big data aid decision-making methods and system constituting method based on fuzzy reasoning logic, the system utilizes the historical data and Mamdani Fuzzy Logic Reasoning of hospital's detection, the processing method of comentropy is used to the weight of each disease indicators, a kind of new prostate cancer detection model based on Mamdani fuzzy inference system is constructed, with aiding in the clinical stages for judging disease；The auxiliary system will be statisticallyd analyze and be combined with medical data decision, can provide fast and accurately therapeutic scheme automatically for doctor；The system can compare according to the physical signs at different Diagnostic Time intervals, and the progress of prostate cancer can be monitored in real time, and doctor can assess definitive treatment scheme to the curative effect of patient by the system.
Description
Technical field
The invention belongs to artificial intelligence field, in particular to a kind of prostate cancer big data based on fuzzy reasoning logic is auxiliary
Help decision-making technique and system constituting method.
Background technique
Using the medical conditions of intelligent medical system (expert system) Lai Gaishan developing country.In intelligent medical system
Under help, doctor or medical expert can be combined the supplemental treatment regimens of mechanical-assisted mode with the diagnostic experiences of oneself,
Make more reliable Treatment decsion.In fact, assessed by statistics relevant to tumor markers in pathological replacement and
Determine the clinical stages of prostate cancer, this is a cumbersome and duplicate job.Therefore, these tasks can assist system in machine
It is completed in system.
In addition, Internet of Things (IoT) can be applied to the medical field of developing country according to machine auxiliary system.Hospital,
Timely and effectively medical treatment communication is established between patient, doctor, doctor is made to submit significant diagnostic message in time, and patient obtains real
When medical report.Therefore, intelligent medical system can be effectively improved discordant social relationships between doctors and patients.
Summary of the invention
In view of the above deficiencies, a kind of intelligence that prostate cancer big data aid decision is carried out using fuzzy reasoning logic is proposed
Energy system and system constituting method, fuzzy inference system, will be with various disease indicators (tumours by manually and automatically adjusting weight
Marker) fusion of relevant medical information, model is constructed, is provided assistance in diagnosis tool and side for the clinical stages of prostate cancer
Method.
A kind of prostate cancer big data aid decision-making system construction method based on fuzzy reasoning logic, including following step
It is rapid:
Step 1: obtaining hospital patient history prostate cancer detection and diagnosis data；
The prostate cancer detection data includes column gland cancer disease indicators and PEV, and the prostatic disorders index includes
TPSA, RBC, Hb, FPSA, PAP, PSMA, the prostate cancer diagnosis data include patient's present illness belonging to by stages, the I phase,
II phase, III phase, IV phase }；
Step 2: being based on prostate cancer disease metric history data, each prostate cancer disease index is calculated using comentropy
Weight；
Step 3: by diagnosis of prostate disease index be divided into two class C (t)={ TPSA, FPSA, Hb, RBC } and M (t)=
{ PAP, PSMA } constructs prostate cancer main association and secondary association computation model SC using C (t) and M (t) detected value and weight respectively
(t) and PC (t)；
Step 4: utilizing the weight of each prostate cancer disease index, between calculating patient when detecting when t, the main pass of prostate cancer
Connection and secondary association correlation；
Step 5: being based on hospital patient history prostate cancer diagnosis data, using trichotomy, construct stages of prostate cancer and close
In ADPCa(i) subordinating degree function；
Step 6: random setting { a1,a2,σ1,σ2And each PEV value interval point by stages, successively utilize hospital patient history
Subordinating degree function of the prostate cancer historical data based on building calculates the phase of the history prostate cancer PEV of patient using centroid method
Position estimated value, if be more than 90% patient detected value PEV fall into setting in the consistent PEV value of conclusion by stages section,
Before obtaining currently by the building of the subordinating degree function of correlation calculations model and stages of prostate cancer based on fuzzy reasoning logic
Otherwise column gland cancer big data aid decision-making system readjusts { a1,a2,σ1,σ2And each PEV value interval point by stages, it repeats
Step 6；
Wherein, { a1,σ1And { a2,σ2Stages of prostate cancer is respectively indicated about ADPCa(i) first in subordinating degree function
The mean value and variance of subordinating degree function and the second subordinating degree function, the second subordinating degree function and third subordinating degree function separation.
After it will test index progress Fuzzy Processing, fuzzy corresponding, the fuzzy correspondence of building is carried out with staging diagnosis result
Relationship forms intelligentized auxiliary diagnostic tool, simplifies the manual procedure of data, accelerates processing speed, can be with
Using the system real-time monitoring physiological indexes situation.
Further, the calculation formula that the weight of each prostate cancer disease index is calculated using comentropy is as follows:
Wherein,Indicate j-th of prostate cancer disease index TM(j)Optimal weight, λTM(j)And wTM(j)It respectively indicates
Jth prostate cancer disease indexTM(j)Weight parameter regulatory factor and weighted value,
λTM(j)={ λTPSA,λFPSA,λRBC,λHb,λPAP,λPSMA, λTM(j)Value rule of thumb set by doctor, value model
It encloses for [0,1], wTM(j)={ wTPSA,wFPSA,wRBC,wHb,wPAP,wPSMA}；Indicate i-th of patient P aiIn acquisition
In hospital patient historical data, j-th of prostate cancer diagnosis indexTM(j)Detection mean value；M indicates the hospital patient history obtained
The number of patients for including in data, dTM(j), ETM(j),Belong to intermediate variable.
The weight of each disease indicators is handled using the method for comentropy, so that the parameter in the auxiliary system is more quasi-
Really, effectively.
Further, the correlation calculations model SC (t) and PC (t) of prostate cancer primary and secondary disease are as follows:
Wherein, δTPSA(t), δRBC(t), δHb(t), δFPSA(t), δPAP(t), δPSMA(t) patient is respectively indicated in time t,
The detected value of 6 diagnosis indexes TPSA, RBC, Hb, FPSA, PAP, PSMA of prostate cancer；δTPSA(i), δRBC(i), δHb(i),
δFPSA(i), δPAP(i), δPSMA(i) respectively indicate patient 6 diagnosis index TPSA, RBC of 1 year prostate cancer, Hb,
The detected value of FPSA, PAP, PSMA,Indicate that history detects number.
Further, using subordinating degree function of the hospital patient history prostate cancer historical data based on building, disease is calculated
The history prostate cancer detected value PEV of people, use specific formula is as follows:
Wherein, xs ADAnd ys MDPatient is respectively indicated in the corresponding disease indicators correlation of time s and is subordinate to angle value, n is indicated
The inspection number in patient's current check period, wherein patient is in the corresponding SC (t) of time S and PC (t), if SC (t) and PC (t) is same
When the SC that gives less than hospital in the critical value of II phase and III phase, then xs ADValue be corresponding SC (t), otherwise, xs ADTake
Value is corresponding PC (t).
Further, constructed stages of prostate cancer is about ADPCa(i) subordinating degree function is as follows:
The method that prostate cancer big data aid decision-making system described in a kind of application carries out aid decision, obtains patient's
Prostate cancer disease diagnosis index inputs the prostate cancer big data decision system based on fuzzy reasoning logic, according to doctor
Respectively middle SC (t) and the corresponding section PC (t), acquisition patient are subordinate to angle value to the prostate cancer of institute's setting by stages, and foundation is subordinate to angle value
PEV value is calculated, corresponding each PEV value section by stages obtains assisting prediction result by stages belonging to patient's prostate cancer.
Beneficial effect
The present invention provides a kind of prostate cancer big data aid decision-making method and system structure based on fuzzy reasoning logic
Construction method, the system adopt the weight of each disease indicators using the historical data and Mamdani Fuzzy Logic Reasoning of hospital's detection
With the processing method of comentropy, a kind of new prostate cancer detection model based on Mamdani fuzzy inference system is constructed, is used
Aid in the clinical stages for judging disease；The auxiliary system will be statisticallyd analyze and be combined with medical data decision, can be automatically
Doctor provides fast and accurately therapeutic scheme；The system can compare according to the physical signs at different Diagnostic Time intervals, can be with
The progress of real-time monitoring prostate cancer, doctor can assess definitive treatment scheme to the curative effect of patient by the system.
Machine auxiliary diagnosis is combined with artificial judgment, is of great significance to the final Treatment decsion of medical worker.
Detailed description of the invention
Fig. 1 be the present invention in example described in system building schematic diagram；
Fig. 2 be the present invention in example in disease association three different stage membership function schematic diagrames；
Fig. 3 be the present invention in example in three different stage membership functions ambiguity solution control result schematic diagram.
Specific embodiment
Below in conjunction with drawings and examples, the present invention is described further.
As shown in Figure 1, a kind of prostate cancer big data aid decision-making system construction method based on fuzzy reasoning logic, packet
Include following steps:
Step 1: obtaining hospital patient history prostate cancer detection and diagnosis data；
The prostate cancer detection data includes column gland cancer disease indicators and PEV, and the prostatic disorders index includes
TPSA, RBC, Hb, FPSA, PAP, PSMA, the prostate cancer diagnosis data include patient's present illness belonging to by stages, the I phase,
II phase, III phase, IV phase }；
Step 2: being based on prostate cancer disease metric history data, each prostate cancer disease index is calculated using comentropy
Weight；
The calculation formula for calculating the weight of each prostate cancer disease index using comentropy is as follows:
Wherein,Indicate j-th of prostate cancer disease index TM(j)Optimal weight, λTM(j)And wTM(j)It respectively indicates
Jth prostate cancer disease indexTM(j)Weight parameter regulatory factor and weighted value,
λTM(j)={ λTPSA,λFPSA,λRBC,λHb,λPAP,λPSMA, λTM(j)Value rule of thumb set by doctor, value model
It encloses for [0,1], wTM(j)={ wTPSA,wFPSA,wRBC,wHb,wPAP,wPSMA}；Indicate i-th of patient P aiIn acquisition
In hospital patient historical data, j-th of prostate cancer diagnosis indexTM(j)Detection mean value；M indicates the hospital patient history obtained
The number of patients for including in data, dTM(j), ETM(j),Belong to intermediate variable.
The weight of each disease indicators is handled using the method for comentropy, so that the parameter in the auxiliary system is more quasi-
Really, effectively.
Step 3: by diagnosis of prostate disease index be divided into two class C (t)={ TPSA, FPSA, Hb, RBC } and M (t)=
{ PAP, PSMA } constructs prostate cancer main association and secondary association computation model SC using C (t) and M (t) detected value and weight respectively
(t) and PC (t)；
The correlation calculations model SC (t) and PC (t) of prostate cancer primary and secondary disease are as follows:
Wherein, δTPSA(t), δRBC(t), δHb(t), δFPSA(t), δPAP(t), δPSMA(t) patient is respectively indicated in time t,
The detected value of 6 diagnosis indexes TPSA, RBC, Hb, FPSA, PAP, PSMA of prostate cancer；δTPSA(i), δRBC(i), δHb(i),
δFPSA(i), δPAP(i), δPSMA(i) respectively indicate patient 6 diagnosis index TPSA, RBC of 1 year prostate cancer, Hb,
The detected value of FPSA, PAP, PSMA,Indicate that history detects number.
Step 4: utilizing the weight of each prostate cancer disease index, between calculating patient when detecting when t, the main pass of prostate cancer
Connection and secondary association correlation；
Step 5: being based on hospital patient history prostate cancer diagnosis data, using trichotomy, construct stages of prostate cancer and close
In ADPCa(i) subordinating degree function；
Step 6: random setting { a1,a2,σ1,σ2And each PEV value interval point by stages, successively utilize hospital patient history
Subordinating degree function of the prostate cancer historical data based on building calculates the phase of the history prostate cancer PEV of patient using centroid method
Position estimated value, if be more than 90% patient detected value PEV fall into setting in the consistent PEV value of conclusion by stages section,
Before obtaining currently by the building of the subordinating degree function of correlation calculations model and stages of prostate cancer based on fuzzy reasoning logic
Otherwise column gland cancer big data aid decision-making system readjusts { a1,a2,σ1,σ2And each PEV value interval point by stages, it repeats
Step 6；
Wherein, { a1,σ1And { a2,σ2Stages of prostate cancer is respectively indicated about ADPCa(i) first in subordinating degree function
The mean value and variance of subordinating degree function and the second subordinating degree function, the second subordinating degree function and third subordinating degree function separation.
As shown in Fig. 2, constructed stages of prostate cancer is about ADPCa(i) subordinating degree function is as follows:
Using subordinating degree function of the hospital patient history prostate cancer historical data based on building, before the history for calculating patient
Column gland cancer detected value PEV, use specific formula is as follows:
Wherein, xs ADAnd ys MDPatient is respectively indicated in the corresponding disease indicators correlation of time s and is subordinate to angle value, n is indicated
The inspection number in patient's current check period, wherein patient is in the corresponding SC (t) of time S and PC (t), if SC (t) and PC (t) is same
When the SC that gives less than hospital in the critical value of II phase and III phase, then xs ADValue be corresponding SC (t), otherwise, xs ADTake
Value is corresponding PC (t).
After it will test index progress Fuzzy Processing, fuzzy corresponding, the fuzzy correspondence of building is carried out with staging diagnosis result
Relationship forms intelligentized auxiliary diagnostic tool, simplifies the manual procedure of data, accelerates processing speed, can be with
Using the system real-time monitoring physiological indexes situation.
The method that prostate cancer big data aid decision-making system described in a kind of application carries out aid decision, obtains patient's
Prostate cancer disease diagnosis index inputs the prostate cancer big data decision system based on fuzzy reasoning logic, according to doctor
Respectively middle SC (t) and the corresponding section PC (t), acquisition patient are subordinate to angle value to the prostate cancer of institute's setting by stages, and foundation is subordinate to angle value
PEV value is calculated, corresponding each PEV value section by stages obtains assisting prediction result by stages belonging to patient's prostate cancer；In this example
Subordinating degree function ambiguity solution control result it is as shown in Figure 3.
Doctor obtains PEV value by the system, and the auxiliary diagnosis of disease situation of change is carried out using the size of the PEV value.
In this embodiment, used medical information is from three first-class hospital, institute, China: Xiang Ya hospital, refined second doctor in Hunan
Institute, Xiang Ya third hospital.Information records center is collected according to the not homologous ray of three hospitals, classification, pre-processes and integrate with before
The relevant all kinds of medical datas of column gland cancer.The curative effect and patient's physical signs of the main reflection therapeutic choice of these statistics are entirely being examined
Variation in the disconnected period.In addition, with regard to the mean apparent to 2015 Nian Sanjia hospital cases for prostate cancer key parameters in 2011 and
Speech, during 2011 to 2015, a large amount of medical datas related with prostate cancer are stringent by the not homologous ray of three hospitals
Record, pretreatment and classification.In order to guarantee the accuracy and reasonability of experiment, we are extracted from more than 8000 patients diagnosed
23658 structurings and identifiable medical information.
During 2011 to 2015, the average behavior of TPSA slowly rises to 20.17ng/ml from 18.63ng/ml,
Reach maximum value 45.2ng/ml within 2013, illustrates that the state of an illness of cancer patient has obtained effective control over nearly 5 years.However, by
In TPSA normal range (NR) 0 between 4ng/ml, those are diagnosed as the case of Pr in past 5 years, three hospitals
Cancer patient is still in physiologic derangement state.Theoretically, people of the TPSA value more than 10 nanograms/milliliters is likely to forefront of suffering hardships
Gland cancer.In addition, patient is possible to suffer from prostate cancer when the mean apparent of TSPA is more than 50ng/ml.Generally speaking, it first rises
The trend Trendline fallen afterwards shows that these cases were gradually recovered from the treatment of doctor decision in past 5 years.
In addition, the performance of FPSA/TPSA be also clinical medicine detection, diagnosing and treating prostate cancer another it is important according to
According to.The normal range (NR) of FPSA/TPSA is ideally equal to or greater than 0.25.It is preceding when the mean apparent of FPSA/TPSA is lower than 0.1
The disease incidence of column gland cancer must be 56% or more.With regard to 2011 to 2015 Nian Sanjia hospital cases for prostate cancer key parameters put down
For showing.According to the medical statistics data between 2011~2014 years, the mean apparent of FPSA/TPSA sharply declines from 0.22
To 0.05, this significantly illustrates that the state of an illness of most of patients with prostate cancer is constantly deteriorating.In addition, these structured medical datas
It further demonstrates that, in past 5 years, most of cases of three hospital diagnosis are in the clinical stage III or IV of prostate cancer
Phase (middle and advanced stage).Fortunately, from 2014 to 2015 year, the health status of these patients with prostate cancer starts gradually to improve,
It is primarily due to doctor and takes some remedy measures, such as drug therapy, excision, radiotherapy, chemotherapy to it.
As prostate cancer diagnosis, diagnosis and the most important index of prognosis, key parameter (PSMA and PAP) should examined entirely
It is analyzed and is assessed in the disconnected period, machine system is enable accurately to make Treatment decsion.In addition, clinical medicine list of notion
Bright, the normal range (NR) of PSMA and PAP are respectively smaller than 4 and 3.5ng/ml.With regard to 2011 to 2015 Nian Sanjia hospital prostate carninomatosis
For the mean apparent of example key parameter, the related statistical data of 5 Nian Laiyu key component of past, which has, first to be risen rapidly afterwards slowly
Downward trend.Further, it should be noted that PAP and PSMA respectively reached the nanograms/milliliter of maximum value 56.2 and 33.78 in 2014.
This has shown from 2011 to 2014 year that the symptom of most of cases is still deteriorating, and since 2014, these symptoms have started
Gradually restore.From the point of view of medicine decision data, doctor can formulate more effective treatment method by expert consulting to control
The state of an illness of patient processed.
The present embodiment is realized on distributed Hadoop and Spark cluster, by HDFS (distributed file system) conduct
Data storage layer builds calculation and programming model as data computation layer, efficiently quickly by Mapreduce and Rdd Computational frame
Parallel data processing constructs the aid decision-making system using construction method of the present invention and algorithm solves influence power maximum
Change start node, and design different comparative experiments analysis start nodes and choose effect and quality, thus proof theory analysis side
The correctness of method.
Machine auxiliary system depends on the clinic point of the disease determined by the system to the treatment recommendations of prostate cancer
Phase.It is most of in 8000 patients just to be found in III, IV phase of prostate cancer since diagnostic interval 1~3, therefore change
Treat the primary treatment suggestion that can be used as the system.Hereafter, aobvious to the periodic evaluation of stages of prostate cancer from diagnostic interval 4 to 8
Show, average Diagnostic parameters drops to 125.29 from 179.88, therefore many alternative medicine of doctor are recommended in this diagnostic period, main
It to include excision, endocrine therapy, radiotherapy or prostatectomy.With the improvement of patients with prostate cancer symptom, machine auxiliary
System will pay the utmost attention to positive monitoring and medications during the diagnostic interval 9 and 10.
The purpose of stages of prostate cancer is the severity of description prostate cancer and the degree that cancer cell is spread in vivo.Cause
This, understand prostate cancer whether be in I, II, III or IV phase for make optimal treatment selection be of great significance.With regard to the past 5
For Nian Sanjia hospital patients with prostate cancer average Diagnostic parameters P EVP Ca relevant to staging, 2011 to 2015
Average P EVP Ca increases nearly 2.1 times, and a mean P EVP Ca rises to 139.44 from 67.29, nearly 5 years population mean P
EVP Ca is about 100, shows that most of prostate cancers are intermittent or high-level (III, IV phase).In addition, 23658 medicine letters
Breath shows in 8000 patients of this 3 hospitals, most of that Late-stage Prostate Cancer is had developed into when being found, this with
Testing result in machine auxiliary system is almost consistent.
Among this real case, the accuracy of diagnosis, which is defined rigorously, to be diagnosed for patient when finding first time
For the probability of prostate cancer.As case load is from 200, continue to increase to 8000, the accuracy rate of diagnosis of physician from
97% drops to 81%, and the accuracy rate of diagnosis of machine auxiliary system is then gradually increased.From 61% to 87%.Especially work as sample
When sum reaches 8000 parts, the diagnostic accuracy of machine auxiliary system is more than doctor for the first time.In addition, when data sample size from
200 when increasing to 8000, and the precision of machine auxiliary system improves about 42.6%.System of the present invention can pass through
It is continuous to increase historical data, the weight of prostate cancer disease index is further updated, so that auxiliary system is more
Accurately.
The above is only the preferred embodiment of the technology of the present invention, it is noted that for the common skill of the art
For art personnel, without departing from the technical principles of the invention, several improvement and replacement can also be made, these improve and
Replacement also should be regarded as protection scope of the present invention.
Claims (6)
1. a kind of prostate cancer big data aid decision-making system construction method based on fuzzy reasoning logic, which is characterized in that packet
Include following steps:
Step 1: obtaining hospital patient history prostate cancer detection and diagnosis data；
The prostate cancer detection data include column gland cancer disease indicators and PEV, the prostatic disorders index include TPSA,
RBC, Hb, FPSA, PAP, PSMA, the prostate cancer diagnosis data include patient's present illness belonging to by stages, the I phase, the II phase,
III phase, IV phase }；
Step 2: being based on prostate cancer disease metric history data, the power of each prostate cancer disease index is calculated using comentropy
Weight；
Step 3: by diagnosis of prostate disease index be divided into two class C (t)={ TPSA, FPSA, Hb, RBC } and M (t)=PAP,
PSMA }, using C (t) and M (t) detected value and weight construct respectively prostate cancer main association and secondary association computation model SC (t) and
PC(t)；
Step 4: using each prostate cancer disease index weight, calculate patient when detecting between t when, prostate cancer main association and
Secondary association correlation；
Step 5: be based on hospital patient history prostate cancer diagnosis data, using trichotomy, construct stages of prostate cancer about
ADPCa(i) subordinating degree function；
Step 6: random setting { a1,a2,σ1,σ2And each PEV value interval point by stages, successively utilize hospital patient history prostate
Subordinating degree function of the cancer historical data based on building calculates the phase estimation of the history prostate cancer PEV of patient using centroid method
Value, if be more than 90% patient detected value PEV fall into setting with the consistent PEV value of conclusion by stages section, worked as
The preceding prostate cancer based on fuzzy reasoning logic constructed by the subordinating degree function of correlation calculations model and stages of prostate cancer
Otherwise big data aid decision-making system readjusts { a1,a2,σ1,σ2And each PEV value interval point by stages, repeat step 6；
Wherein, { a1,σ1And { a2,σ2Stages of prostate cancer is respectively indicated about ADPCa(i) first is subordinate in subordinating degree function
Spend the mean value and variance of function and the second subordinating degree function, the second subordinating degree function and third subordinating degree function separation.
2. the method according to claim 1, wherein calculating the power of each prostate cancer disease index using comentropy
The calculation formula of weight is as follows:
Wherein,Indicate the optimal weight of j-th of prostate cancer disease index TM (j), λTM(j)And wTM(j)Respectively indicate jth
The weight parameter regulatory factor and weighted value of a prostate cancer disease index TM (j),
λTM(j)={ λTPSA,λFPSA,λRBC,λHb,λPAP,λPSMA, λTM(j)Value rule of thumb set by doctor, value range is
[0,1], wTM(j)={ wTPSA,wFPSA,wRBC,wHb,wPAP,wPSMA}；Indicate i-th of patient P aiIn the hospital of acquisition
In patient's history's data, j-th of prostate cancer diagnosis indexTM(j)Detection mean value；M indicates the hospital patient historical data obtained
In include number of patients, dTM(j), ETM(j),Belong to intermediate variable.
3. according to the method described in claim 2, it is characterized in that, the correlation meter of prostate cancer primary and secondary disease
It calculates model SC (t) and PC (t) is as follows:
Wherein, δTPSA(t), δRBC(t), δHb(t), δFPSA(t), δPAP(t), δPSMA(t) patient is respectively indicated in time t, forefront
The detected value of 6 diagnosis indexes TPSA, RBC, Hb, FPSA, PAP, PSMA of gland cancer；δTPSA(i), δRBC(i), δHb(i), δFPSA
(i), δPAP(i), δPSMA(i) respectively indicate patient 6 diagnosis index TPSA, RBC of 1 year prostate cancer, Hb, FPSA,
The detected value of PAP, PSMA,Indicate that history detects number.
4. the method according to claim 1, wherein being based on using hospital patient history prostate cancer historical data
The subordinating degree function of building, calculates the history prostate cancer detected value PEV of patient, use specific formula is as follows:
Wherein, xs ADAnd ys MDPatient is respectively indicated in the corresponding disease indicators correlation of time s and is subordinate to angle value, n indicates patient
The inspection number in current check period, wherein patient is in the corresponding SC (t) of time S and PC (t), if SC (t) and PC (t) is small simultaneously
In the SC that hospital gives in the critical value of II phase and III phase, then xs ADValue be corresponding SC (t), otherwise, xs ADValue be
Corresponding PC (t).
5. method according to claim 1-4, which is characterized in that constructed stages of prostate cancer is about ADPCa
(i) subordinating degree function is as follows:
6. a kind of carry out aid decision using the described in any item prostate cancer big data aid decision-making systems of claim 1-5
Method, which is characterized in that obtain the prostate cancer disease diagnosis index of patient, input the forefront based on fuzzy reasoning logic
Gland cancer big data decision system, prostate cancer according to hospital's setting respectively by stages in SC (t) and the corresponding section PC (t), obtain
Patient is subordinate to angle value, calculates PEV value according to angle value is subordinate to, corresponding each PEV value section by stages obtains belonging to patient's prostate cancer
Prediction result is assisted by stages.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910635587.6A CN110517765B (en) | 2019-07-15 | 2019-07-15 | Prostate cancer big data assistant decision method and system construction method based on fuzzy inference logic |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910635587.6A CN110517765B (en) | 2019-07-15 | 2019-07-15 | Prostate cancer big data assistant decision method and system construction method based on fuzzy inference logic |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110517765A true CN110517765A (en) | 2019-11-29 |
| CN110517765B CN110517765B (en) | 2022-06-14 |
Family
ID=68623633
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910635587.6A Active CN110517765B (en) | 2019-07-15 | 2019-07-15 | Prostate cancer big data assistant decision method and system construction method based on fuzzy inference logic |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110517765B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111312392A (en) * | 2020-03-13 | 2020-06-19 | 中南大学 | Prostate cancer auxiliary analysis method and device based on integration method and electronic equipment |
| CN113707308A (en) * | 2021-08-31 | 2021-11-26 | 平安国际智慧城市科技股份有限公司 | Medical data analysis device and computer readable storage medium |
| CN113793683A (en) * | 2021-08-23 | 2021-12-14 | 广州医科大学附属第一医院（广州呼吸中心） | Prostate cancer aid decision-making method and system based on PSA |
| CN116570848A (en) * | 2023-07-13 | 2023-08-11 | 神州医疗科技股份有限公司 | Radiotherapy clinical auxiliary decision-making method and system based on automatic sketching |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1547149A (en) * | 2003-12-04 | 2004-11-17 | 上海交通大学 | Method for implementing brain glioma computer aided diagnosis system based on data mining |
| WO2009016385A1 (en) * | 2007-07-31 | 2009-02-05 | Imperial Innovations Limited | Methods of aiding in the diagnosis of prostate cancer |
| WO2012102444A1 (en) * | 2011-01-26 | 2012-08-02 | 계명대학교 산학협력단 | Method and system for supporting clinical diagnosis based on hierarchical fuzzy inference |
| CN104424386A (en) * | 2013-08-23 | 2015-03-18 | 北京大学 | Multi-parameter magnetic resonance image based prostate cancer computer auxiliary identification system |
| CN109003671A (en) * | 2018-06-29 | 2018-12-14 | 重庆柚瓣家科技有限公司 | A kind of disease probability calculation system and method based on fuzzy decision |
-
2019
- 2019-07-15 CN CN201910635587.6A patent/CN110517765B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1547149A (en) * | 2003-12-04 | 2004-11-17 | 上海交通大学 | Method for implementing brain glioma computer aided diagnosis system based on data mining |
| WO2009016385A1 (en) * | 2007-07-31 | 2009-02-05 | Imperial Innovations Limited | Methods of aiding in the diagnosis of prostate cancer |
| WO2012102444A1 (en) * | 2011-01-26 | 2012-08-02 | 계명대학교 산학협력단 | Method and system for supporting clinical diagnosis based on hierarchical fuzzy inference |
| CN104424386A (en) * | 2013-08-23 | 2015-03-18 | 北京大学 | Multi-parameter magnetic resonance image based prostate cancer computer auxiliary identification system |
| CN109003671A (en) * | 2018-06-29 | 2018-12-14 | 重庆柚瓣家科技有限公司 | A kind of disease probability calculation system and method based on fuzzy decision |
Non-Patent Citations (7)
| Title |
|---|
| F. S. AHADI AND ET.AL: "Feature-Based classification and diagnosis of breast cancer using fuzzy inference system", 《2017 IEEE INTERNATIONAL CONFERENCE ON INFORMATION AND AUTOMATION (ICIA)》 * |
| S. A. BIYOUKI AND ET.AL: "Fuzzy rule-based expert system for diagnosis of thyroid disease", 《2015 IEEE CONFERENCE ON COMPUTATIONAL INTELLIGENCE IN BIOINFORMATICS AND COMPUTATIONAL BIOLOGY (CIBCB)》 * |
| 丁卫平等: "模糊逻辑推理在电子病历智能辅助诊断***中的应用研究", 《南通大学学报(自然科学版)》 * |
| 万鑫: "模糊推理在疾病辅助诊断***中的应用研究", 《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》 * |
| 张惠康等: "骨肿瘤辅助诊断专家***模糊推理模型", 《第四军医大学学报》 * |
| 裴紫燕等: "模糊逻辑在医学辅助诊断中的应用", 《嘉兴学院学报》 * |
| 陈艳等: "基于粗糙集和模糊推理的医疗诊断***的研究", 《广西科技师范学院学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111312392A (en) * | 2020-03-13 | 2020-06-19 | 中南大学 | Prostate cancer auxiliary analysis method and device based on integration method and electronic equipment |
| CN111312392B (en) * | 2020-03-13 | 2023-08-22 | 中南大学 | Integrated method-based auxiliary analysis method and device for prostate cancer and electronic equipment |
| CN113793683A (en) * | 2021-08-23 | 2021-12-14 | 广州医科大学附属第一医院（广州呼吸中心） | Prostate cancer aid decision-making method and system based on PSA |
| CN113793683B (en) * | 2021-08-23 | 2024-04-02 | 广州医科大学附属第一医院（广州呼吸中心） | PSA-based prostate cancer auxiliary decision-making method and system |
| CN113707308A (en) * | 2021-08-31 | 2021-11-26 | 平安国际智慧城市科技股份有限公司 | Medical data analysis device and computer readable storage medium |
| CN116570848A (en) * | 2023-07-13 | 2023-08-11 | 神州医疗科技股份有限公司 | Radiotherapy clinical auxiliary decision-making method and system based on automatic sketching |
| CN116570848B (en) * | 2023-07-13 | 2023-09-15 | 神州医疗科技股份有限公司 | Radiotherapy clinical auxiliary decision-making system based on automatic sketching |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110517765B (en) | 2022-06-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110517765A (en) | A kind of prostate cancer big data aid decision-making method and system constituting method based on fuzzy reasoning logic | |
| Xu et al. | A risk prediction model for type 2 diabetes based on weighted feature selection of random forest and xgboost ensemble classifier | |
| Iyer et al. | Diagnosis of diabetes using classification mining techniques | |
| Yao et al. | Liver disease screening based on densely connected deep neural networks | |
| Devi et al. | A novel hybrid approach for diagnosing diabetes mellitus using farthest first and support vector machine algorithms | |
| Straszecka | Combining uncertainty and imprecision in models of medical diagnosis | |
| Ramezani et al. | A novel hybrid intelligent system with missing value imputation for diabetes diagnosis | |
| CN104881463A (en) | Reference medical record search method and device based on structural medical record database | |
| Wu et al. | Effective data decision-making and transmission system based on mobile health for chronic disease management in the elderly | |
| Khan et al. | Machine learning techniques for heart disease datasets: A survey | |
| CN110111884B (en) | CMKMC-based man-machine cooperative intelligent medical aid decision-making system | |
| Jain et al. | Improving the prediction rate of diabetes using fuzzy expert system | |
| CN113241196B (en) | Remote medical treatment and grading monitoring system based on cloud-terminal cooperation | |
| Karim et al. | A belief rule based expert system to assess clinical bronchopneumonia suspicion | |
| CN111863238A (en) | Parallel intelligence based chronic disease diagnosis and treatment system and diagnosis and treatment method | |
| CN112365978A (en) | Method and device for establishing early risk assessment model of tachycardia event | |
| CN111081379B (en) | Disease probability decision method and system thereof | |
| CN109686452A (en) | A kind of intelligence system and method formulated for diabetes medicament Intervention Strategy | |
| CN114639479A (en) | Intelligent diagnosis auxiliary system based on medical knowledge map | |
| CN111951975A (en) | Sepsis early warning method based on deep learning model GPT-2 | |
| CN104462858A (en) | Health warning method based on multi-order hidden Markov model | |
| Brause et al. | Septic shock diagnosis by neural networks and rule based systems | |
| Muro et al. | Weighting experience-based decision support on the basis of clinical outcomes' assessment | |
| Shukla et al. | Cloud computing with artificial intelligence techniques for effective disease detection | |
| Anooj | Implementing decision tree fuzzy rules in clinical decision support system after comparing with fuzzy based and neural network based systems |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |